arXiv subjects

Mohammadamin Fazli

Publications and source records attributed to Mohammadamin Fazli.

6 recordsLinked to original sources

arXiv2026

KG-Commit: A Dynamic Knowledge Graph for Online Just-in-Time Software Defect Prediction

Just-in-time software defect prediction (JIT-SDP) aims to identify risky commits as they arrive and provide developers with timely feedback. This need for low latency has led most approaches to rely on commit-level information and overlook the broader project context in which a change occurs. Incorporating this context is challenging because it requires both efficient retrieval for incoming commits and continual maintenance as the repository evolves. We introduce KG-Commit, a dynamic knowledge graph that incrementally maintains repository history, within-file code structure, and commit semantics as the project evolves. It also uses an AST-delta mechanism to track structural changes between file edits and relies on lightweight graph inference running entirely on CPU. Our evaluation on 11 Apache software projects against six baselines shows that KG-Commit achieves the highest aggregate Macro-F1 (0.704), G-Mean (0.706), and AUC (0.809) using our selected inference pipeline. Under a realistic online protocol, it outperforms LR, HGB, RF, and DeepJIT on all 11 projects, LApredict on 10, and JITLine on 9 projects in Macro-F1, with the aggregate paired difference significant in every case. KG-Commit processes each commit in approximately 1.33~s, with a cost that remains stable as the graph grows and is compatible with commit rates observed in real-world projects. These findings show that rich project context can be efficiently maintained and exploited for online JIT-SDP.

cs.SE↗

arXiv2026

Learning Spectral Representations of Code through Latent Graph Learning for Generalizable Cross-Language Code Clone Detection

Current code clone detection (CCD) methods rely on fixed, language-specific graph representations like abstract syntax trees (ASTs) or program dependency graphs (PDGs). Because functionally identical code fragments can yield wildly different structures, these rigid graphs produce non-discriminative spectra that perform close to chance. To address this, we propose SPECTRA-Siam, a Siamese latent graph learning network that learns a latent space such that the graph's spectrum serves as a discriminative signature of code functionality by optimizing downstream CCD performance. Given a fragment's AST and data-dependencies, SPECTRA-Siam induces a fixed-size weighted latent graph through soft slot assignment and multi-head attention, and extracts a multi-scale spectral representation from its normalized Laplacian. Mapping all fragments into this shared space yields comparable spectra across programming languages. Experiments on BigCloneBench, AtCoder, and a four-language CodeNet benchmark (Java, Python, C++, C#) support this design choice. Using the same downstream classifier, moving from fixed to learned latent graphs spectra jumps F1 from 0.37 to 0.67 on BigCloneBench and accuracy from 0.60 to 0.71 on AtCoder. On CodeNet, the full model reaches 0.69 accuracy in four epochs and 0.79 after thirty epochs. In bridge-assisted language transfer across 60 unseen paths, SPECTRA-Siam's performance degrades by only 0.058, versus 0.112--0.228 for baselines, showing that learned graph spectra provide a highly generalizable representation for cross-language clone detection.

cs.SE↗

arXiv2025

Can Invisible Psychological Traits Organize Visible Network Structure? A Complex Network Analysis of Myers-Briggs Type Indicator-Based Interaction Patterns in Anonymous Social Networks

Exploration of the impact of personality traits on social interactions within anonymous online communities poses a challenge at the interface of networked social sciences and psychology. We analyze whether Myers-Briggs Type Indicator (MBTI) personality types impact the dynamics of interactions on an anonymous chat system with over 288,000 messages from 6,076 users. Using a data set including 940 users voluntarily providing MBTI typing and gender, we create a weighted undirected network and apply network-science measures-such as assortativity, centrality measures, and community detection with the Louvain algorithm-to estimate the level of personality-based homophily and heterophily. Contrary to previous observations in structured social settings, our research shows a dominance of heterophilous interactions (89.3%), particularly among cognitively complementary types, i.e., NT (Intuitive-Thinking) and NF (Intuitive-Feeling). However, there is a moderate level of personality-based homophily (10.7%), notably among introverted intuitive personalities (e.g., INTJ, INFP, INFJ), reflecting an underlying cognitive alignment that persists regardless of identity markers. The interaction network exhibits scale-free properties with a power-law exponent of 1.45. In contrast, gender is a stronger homophily attribute, as evidenced by stronger levels of female users' group interactions compared with male users. While MBTI type influences minor interaction preferences, community structure exhibits low modularity (Q = 0.2584). The findings indicate that, in the absence of identity cues, psychological traits subtly shape online behavior, blending exploratory heterophily with subtle homophilic inclinations.

cs.SI↗

arXiv2025

NAZM: Network Analysis of Zonal Metrics in Persian Poetic Tradition

This study formalizes a computational model to simulate classical Persian poets' dynamics of influence through constructing a multi-dimensional similarity network. Using a rigorously curated dataset based on Ganjoor's corpus, we draw upon semantic, lexical, stylistic, thematic, and metrical features to demarcate each poet's corpus. Each is contained within weighted similarity matrices, which are then appended to generate an aggregate graph showing poet-to-poet influence. Further network investigation is carried out to identify key poets, style hubs, and bridging poets by calculating degree, closeness, betweenness, eigenvector, and Katz centrality measures. Further, for typological insight, we use the Louvain community detection algorithm to demarcate clusters of poets sharing both style and theme coherence, which correspond closely to acknowledged schools of literature like Sabk-e Hindi, Sabk-e Khorasani, and the Bazgasht-e Adabi phenomenon. Our findings provide a new data-driven view of Persian literature distinguished between canonical significance and interextual influence, thus highlighting relatively lesser-known figures who hold great structural significance. Combining computational linguistics with literary study, this paper produces an interpretable and scalable model for poetic tradition, enabling retrospective reflection as well as forward-looking research within digital humanities.

cs.SI↗

arXiv2024

SDPERL: A Framework for Software Defect Prediction Using Ensemble Feature Extraction and Reinforcement Learning

Ensuring software quality remains a critical challenge in complex and dynamic development environments, where software defects can result in significant operational and financial risks. This paper proposes an innovative framework for software defect prediction that combines ensemble feature extraction with reinforcement learning (RL)--based feature selection. We claim that this work is among the first in recent efforts to address this challenge at the file-level granularity. The framework extracts diverse semantic and structural features from source code using five code-specific pre-trained models. Feature selection is enhanced through a custom-defined embedding space tailored to represent feature interactions, coupled with a pheromone table mechanism inspired by Ant Colony Optimization (ACO) to guide the RL agent effectively. Using the Proximal Policy Optimization (PPO) algorithm, the proposed method dynamically identifies the most predictive features for defect detection. Experimental evaluations conducted on the PROMISE dataset highlight the framework's superior performance on the F1-Score metric, achieving an average improvement of $6.25\%$ over traditional methods and baseline models across diverse datasets. This study underscores the potential for integrating ensemble learning and RL for adaptive and scalable defect prediction in modern software systems.

cs.SE↗

arXiv2020

Predicting Subjective Features of Questions of QA Websites using BERT

Community Question-Answering websites, such as StackOverflow and Quora, expect users to follow specific guidelines in order to maintain content quality. These systems mainly rely on community reports for assessing contents, which has serious problems such as the slow handling of violations, the loss of normal and experienced users' time, the low quality of some reports, and discouraging feedback to new users. Therefore, with the overall goal of providing solutions for automating moderation actions in Q&A websites, we aim to provide a model to predict 20 quality or subjective aspects of questions in QA websites. To this end, we used data gathered by the CrowdSource team at Google Research in 2019 and a fine-tuned pre-trained BERT model on our problem. Based on the evaluation by Mean-Squared-Error (MSE), the model achieved a value of 0.046 after 2 epochs of training, which did not improve substantially in the next ones. Results confirm that by simple fine-tuning, we can achieve accurate models in little time and on less amount of data.

cs.CL↗